Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.7720. Min Act: -0.1700
Data Index: 2926720 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.7095. Min Act: -0.1700
Data Index: 1667390 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.5533. Min Act: -0.1700
Data Index: 3828738 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.4595. Min Act: -0.1700
Data Index: 6935948 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.3345. Min Act: -0.1700
Data Index: 8666821 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.2720. Min Act: -0.1700
Data Index: 1224800 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.2408. Min Act: -0.1700
Data Index: 7005184 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.2408. Min Act: -0.1700
Data Index: 6560199 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.2095. Min Act: -0.1700
Data Index: 5168770 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.1470. Min Act: -0.1700
Data Index: 4237594 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.1158. Min Act: -0.1700
Data Index: 1787498 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.0845. Min Act: -0.1700
Data Index: 7123143 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.0220. Min Act: -0.1700
Data Index: 6999012 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.0533. Min Act: -0.1700
Data Index: 4988385 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.0220. Min Act: -0.1700
Data Index: 8021530 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.0220. Min Act: -0.1700
Data Index: 4645461 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7720. Min Range: -7.7720
Max Act: 6.9908. Min Act: -0.1700
Data Index: 4973096 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7720. Min Range: -7.7720
Max Act: 6.9595. Min Act: -0.1700
Data Index: 4551230 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7720. Min Range: -7.7720
Max Act: 7.0220. Min Act: -0.1700
Data Index: 8555626 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7720. Min Range: -7.7720
Max Act: 6.9595. Min Act: -0.1700
Data Index: 8017745 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19